{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T03:19:21Z","timestamp":1752549561258},"reference-count":44,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.23919\/apsipa.2018.8659619","type":"proceedings-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T23:11:49Z","timestamp":1552950709000},"page":"1448-1455","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised Pattern Discovery from Thematic Speech Archives Based on Multilingual Bottleneck Features"],"prefix":"10.23919","author":[{"given":"Man-Ling","family":"Sung","sequence":"first","affiliation":[]},{"given":"Siyuan","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Tan","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus","year":"1993","author":"john","key":"ref39"},{"key":"ref38","article-title":"Levenshtein distance","author":"pieterse","year":"2015","journal-title":"Dictionary of Algorithms and Data Structures"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.04.008"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00146"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"journal-title":"Clustering Algorithms","year":"1975","author":"hartigan","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(81)90087-5"},{"journal-title":"Ward's Hierarchical Clustering Method Clustering Criterion and Agglomerative Algorithm","year":"2011","author":"murtagh","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500845"},{"journal-title":"Massachusetts Institute of Technology MIT OpenCourse Ware","year":"0","author":"durphy","key":"ref10"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495637"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2387382"},{"key":"ref14","first-page":"3189","article-title":"Parallel inference of Dirichlet process Gaussian mixture models for unsupervised acoustic modeling: A feasibility study","author":"chen","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1693","DOI":"10.21437\/Interspeech.2011-184","article-title":"Towards unsupervised training of speaker independent acoustic models","author":"jansen","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639241"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855085"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179087"},{"key":"ref19","first-page":"3199","article-title":"A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge","author":"renshaw","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"269","DOI":"10.21437\/Interspeech.2017-513","article-title":"Investigating bidirectional recurrent neural network language models for speech recognition","author":"chen","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289081"},{"key":"ref5","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref8","article-title":"The zero resource speech challenge 2017","author":"dunbar","year":"2017","journal-title":"Proc ASRU"},{"key":"ref7","article-title":"The zero resource speech challenge 2015","author":"versteegh","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"949","DOI":"10.21437\/Interspeech.2017-1296","article-title":"Advances in joint CTC-attention based end-to-end speech recognition with a deep cnn encoder and rnn-lm","author":"hori","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268952"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"132","DOI":"10.21437\/Interspeech.2017-405","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref20","first-page":"727","article-title":"Multilingual bottleneck feature learning from untranscribed speech","author":"chen","year":"2017","journal-title":"Proc ASRU"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918442"},{"key":"ref21","first-page":"3989","article-title":"Unsupervised optimal phoneme segmentation: Objectives, algorithm and comparisons","author":"qiao","year":"2008","journal-title":"Proc ICASSP"},{"key":"ref42","article-title":"An introduction to corpora resources of 863 program for chinese language processing and human-machine interaction","author":"qian","year":"2004","journal-title":"Proc ALR2004 affiliated to IJCNLP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319337"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00101-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289081"},{"key":"ref44","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref26","article-title":"An evaluation of graph clustering methods for unsupervised term discovery","author":"lyzinski","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref43","first-page":"480","article-title":"Open source german distant speech recognition: Corpus and acoustic model","author":"radeck-arneth","year":"2015","journal-title":"International Conference on Text Speech and Dialogue"},{"key":"ref25","first-page":"501","article-title":"A segment model based approach to speech recognition","author":"lee","year":"1988","journal-title":"Proc ICASSP"}],"event":{"name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2018,11,12]]},"location":"Honolulu, HI, USA","end":{"date-parts":[[2018,11,15]]}},"container-title":["2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8648538\/8659446\/08659619.pdf?arnumber=8659619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T16:47:18Z","timestamp":1694710038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8659619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":44,"URL":"https:\/\/doi.org\/10.23919\/apsipa.2018.8659619","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}